[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78FENWZS01MB4PMGX6801X6":3,"skill-same:01M78FENWZS01MB4PMGX6801X6":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M78FENWZS01MB4PMGX6801X6","source-command-sr-loop",null,"Converging cleanup loop: repeat \u002Fsimplify until clean, then repeat \u002Fcode-review --fix until clean","jl-cmd-projects\u002Fclaude-dev-env","jl-cmd-projects","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F338158757?v=4","01M78F4M55P4QY5YPN27XBQA9N","01M78F4M65AGEYC88NV6PW4715",7,"MIT","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsource-command-sr-loop\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"source-command-sr-loop\"\ndescription: \"Converging cleanup loop: repeat \u002Fsimplify until clean, then repeat \u002Fcode-review --fix until clean\"\n---\n\n# source-command-sr-loop\n\nUse this skill when the user asks to run the migrated source command `sr-loop`.\n\n## Command Template\n\nRun the converging cleanup loop on the target the user names (a PR URL,\na branch, or blank for the current branch's diff). Each phase invokes an\nexisting skill and repeats it until a pass returns zero new findings.\n\n### Nit-only terminal\n\nWhen a pass finds only nits, apply them, run scoped checks, commit, and push.\nTreat that phase as clean. Do not run another simplify or review pass without\nthe user's request. If later work creates an uncommitted out-of-scope diff,\nstop and report it. Do not inspect, repair, commit, or adopt that diff without\nnew user instruction.\n\n### Effort\n\nSet every model call to `max` effort. If that model has no `max` effort, use\n`xhigh`.\n\n### Stack context\n\nBefore any fixes, load and review the full PR stack, from its base through the\ntarget PR. Read every PR and diff in the stack. Use that full context to judge\neach proposed simplify or code-review fix. Apply a fix only when it fits the\nstack's design, intent, and changes.\n\n### Phase A — loop simplify\n\n1. Invoke the `simplify` skill (or its local equivalent, e.g. `e-simplify`)\n   on the target. Let it run its 4-lens review fan-out (reuse,\n   simplification, efficiency, altitude) and apply its fixes.\n2. After each pass: run the scoped test suite (test files beside the touched\n   code, not the full repo suite), commit once (commit body via\n   `git commit -F \u003Cfile>`, 10-minute timeout — the pre-commit gate runs its\n   own tests), and push to the PR head branch. The PR stays draft.\n3. Repeat the invocation only after substantive findings or a user request.\n   Skips are sticky: carry every adjudicated skip\n   forward into the next pass as \"already adjudicated — do not re-report: ...\"\n   context, or the loop never converges.\n4. Phase A converges when a full pass returns zero new findings. When the\n   previous pass changed only a line or two, a single combined-lens\n   confirmation agent may serve as the final pass.\n\n### Phase B — loop code-review with fixes\n\n1. Run the real code-review command through a headless subprocess in the\n   target worktree: `claude -p \"\u002Fcode-review low --fix\" --max-turns 40` with a\n   10-minute timeout, reading its final text for findings and applied fixes.\n   (The skill's `disable-model-invocation` flag blocks only programmatic tool\n   starts; a `-p` prompt arrives as user input and loads normally.) Fallback\n   when the headless run fails: invoke the `e-code-review` skill with\n   `low --fix` — same review-and-fix contract, no invocation restriction.\n2. After any pass that changed files: test, commit, push as in Phase A.\n3. Repeat until a pass reports zero findings. A nit-only pass ends this phase\n   after its fixes are pushed.\n\n### Finish\n\nWhen both phases are clean, or only fixed nits remain, mark the target PR ready\nwith `gh pr ready`. Confirm that it is no longer a draft.\n\nReport: passes run per phase, commits pushed with hashes, fixes applied, and\nthe standing skip list with reasons.\n\n### Constraints (observed under headless runs)\n\n- Run this loop in the main conversation. A wrapper subagent cannot see the\n  review skills, and a nested agent's own subagent reports route to the main\n  conversation instead of back to it.\n- Scope test runs to the touched files; a full-suite run can outlive one\n  foreground tool call.\n- A hung or newly slow test suite is a finding to investigate, not an\n  inconvenience.\n","# source-command-sr-loop\n\nUse this skill when the user asks to run the migrated source command `sr-loop`.\n\n## Command Template\n\nRun the converging cleanup loop on the target the user names (a PR URL,\na branch, or blank for the current branch's diff). Each phase invokes an\nexisting skill and repeats it until a pass returns zero new findings.\n\n### Nit-only terminal\n\nWhen a pass finds only nits, apply them, run scoped checks, commit, and push.\nTreat that phase as clean. Do not run another simplify or review pass without\nthe user's request. If later work creates an uncommitted out-of-scope diff,\nstop and report it. Do not inspect, repair, commit, or adopt that diff without\nnew user instruction.\n\n### Effort\n\nSet every model call to `max` effort. If that model has no `max` effort, use\n`xhigh`.\n\n### Stack context\n\nBefore any fixes, load and review the full PR stack, from its base through the\ntarget PR. Read every PR and diff in the stack. Use that full context to judge\neach proposed simplify or code-review fix. Apply a fix only when it fits the\nstack's design, intent, and changes.\n\n### Phase A — loop simplify\n\n1. Invoke the `simplify` skill (or its local equivalent, e.g. `e-simplify`)\n   on the target. Let it run its 4-lens review fan-out (reuse,\n   simplification, efficiency, altitude) and apply its fixes.\n2. After each pass: run the scoped test suite (test files beside the touched\n   code, not the full repo suite), commit once (commit body via\n   `git commit -F \u003Cfile>`, 10-minute timeout — the pre-commit gate runs its\n   own tests), and push to the PR head branch. The PR stays draft.\n3. Repeat the invocation only after substantive findings or a user request.\n   Skips are sticky: carry every adjudicated skip\n   forward into the next pass as \"already adjudicated — do not re-report: ...\"\n   context, or the loop never converges.\n4. Phase A converges when a full pass returns zero new findings. When the\n   previous pass changed only a line or two, a single combined-lens\n   confirmation agent may serve as the final pass.\n\n### Phase B — loop code-review with fixes\n\n1. Run the real code-review command through a headless subprocess in the\n   target worktree: `claude -p \"\u002Fcode-review low --fix\" --max-turns 40` with a\n   10-minute timeout, reading its final text for findings and applied fixes.\n   (The skill's `disable-model-invocation` flag blocks only programmatic tool\n   starts; a `-p` prompt arrives as user input and loads normally.) Fallback\n   when the headless run fails: invoke the `e-code-review` skill with\n   `low --fix` — same review-and-fix contract, no invocation restriction.\n2. After any pass that changed files: test, commit, push as in Phase A.\n3. Repeat until a pass reports zero findings. A nit-only pass ends this phase\n   after its fixes are pushed.\n\n### Finish\n\nWhen both phases are clean, or only fixed nits remain, mark the target PR ready\nwith `gh pr ready`. Confirm that it is no longer a draft.\n\nReport: passes run per phase, commits pushed with hashes, fixes applied, and\nthe standing skip list with reasons.\n\n### Constraints (observed under headless runs)\n\n- Run this loop in the main conversation. A wrapper subagent cannot see the\n  review skills, and a nested agent's own subagent reports route to the main\n  conversation instead of back to it.\n- Scope test runs to the touched files; a full-suite run can outlive one\n  foreground tool call.\n- A hung or newly slow test suite is a finding to investigate, not an\n  inconvenience.\n",{"name":5,"description":7},"main","974284b42eeb4609e94d4ebc1f6e36df400d54ca","skill-archive\u002Fsource-command-sr-loop",1,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects","2026-11-15 05:02:47",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add jl-cmd-projects\u002Fclaude-dev-env --skill source-command-sr-loop",{"tool":36,"command":37},"bunx","bunx skills add jl-cmd-projects\u002Fclaude-dev-env --skill source-command-sr-loop",{"tool":39,"command":40},"pnpm","pnpm dlx skills add jl-cmd-projects\u002Fclaude-dev-env --skill source-command-sr-loop","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsource-command-sr-loop\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M78FER7S09AE87MMJFT1E87E","update","Fast-forwards a local repository's main branch to a remote's main after confirming the repo path and source remote through AskUserQuestion. Use when the user says '\u002Fupdate', 'update main', 'fast-forward main', 'sync main from origin', 'pull latest main into \u003Cpath>', or 'bring main up to date'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fupdate\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M78FEGZ7JDWEG3RM78M9Y8F8","skill-builder","Skill lifecycle: classify, scaffold, write via the skill-writer-agent, self-audit, compose sub-skills, polish description triggers, enforce deterministic scripts. Triggers: build a skill, new skill workflow, improve this skill, optimize skill description, skill development lifecycle, skill modularity, skill composition, description trigger catalog, deterministic skill scripts.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fskill-builder\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M78FEDEYHJYKTER9S566DMEZ","session-tidy","Audit, clean, and consolidate session logs in the Obsidian vault. Fixes format drift, resolves orphaned next-steps, updates stale statuses, and generates project rollup summaries. Use when session logs feel cluttered or before starting a new project milestone. Triggers on '\u002Fsession-tidy', 'tidy sessions', 'clean up session logs', 'session audit'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsession-tidy\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M78FE8QR789SKBF3A78N2T13","session-log","Logs a session report as an HTML page, tracks vault context, extracts decisions, and outputs a \u002Frename command. Use for \u002Fsession-log, 'journal this session', 'log this work', 'session report', 'summarize\u002Flog\u002Frecord this session', 'save session', 'capture session', or 'document what we did'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsession-log\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M78FE4JDJHKTJPWRWNQEX2HT","run-claude-dev-env","Build, install, run, and test the claude-dev-env installer. Use when asked to run claude-dev-env, install the Claude Code config into ~\u002F.claude, drive the installer, smoke-test it against a sandbox, or run its test suite.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Frun-claude-dev-env\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M78FE1F0V4N9XB32KE4A2S9D","review-tier","Classify `review_tier_constants` from change axes, hard triggers, and user overrides. Triggers: \u002Freview-tier, tier override, and review classification.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Freview-tier\u002FSKILL.md",[],[]]